© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84679
    Prev
    Next
    INDEX
    Explanations

    existential or experiential concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    訁
    -2.84
     desembar
    -2.73
    憮
    -2.48
    絎
    -2.47
    糁
    -2.45
     lavoratori
    -2.44
     nemico
    -2.42
    盦
    -2.38
     dipendenti
    -2.36
    瘊
    -2.36
    POSITIVE LOGITS
    ”
    2.92
    \
    2.84
     /
    2.84
    <strong>
    2.83
    ↵
    2.70
    *
    2.66
    V
    2.63
    <em>
    2.59
    F
    2.59
    Z
    2.56
    Activations Density 0.002%

    No Known Activations